paul-buerkner/brms

Multivariate asymmetric Laplace Distribution

Open

#728 建立於 2019年8月9日

在 GitHub 查看
 (2 留言) (0 反應) (0 負責人)R (1,402 star) (220 fork)batch import
familyfeaturegood first issue

描述

Hi,

It would be great if you incorporated multivariate version of asymmetric Laplace distribution in brms. Here is the paper that describes its properties: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.496.9720&rep=rep1&type=pdf . I am also attaching wikipedia article about it: https://en.wikipedia.org/wiki/Multivariate_Laplace_distribution . (This one has same authors as the reference papers).

貢獻者指南

技術棧
無
領域
datamachine learning
議題類型
feature
難度面向新貢獻者的預計實作難度，1 表示很小改動，5 表示專家級工作。
5
預計時間有經驗貢獻者完成調查、實作、測試並準備 pull request 的粗略時間範圍。
over 1 week
活動狀態議題目前的可參與程度：新鮮、活躍、陳舊、阻塞或等待維護者輸入。
stale
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
clear
前置要求
R package developmentStan probabilistic programming languageBayesian statisticsmultivariate distribution theory
新手友善度1-100 的估計分數，表示該議題對首次貢獻者的友善程度。
10
研究方向
The issue requests adding a multivariate asymmetric Laplace distribution to the brms package. Implementation would require studying the referenced paper (citeseerx.ist.psu.edu) and Wikipedia article, then writing Stan code for the distribution's log density and random number generation, and integrating it into brms' R interface. Existing similar distributions in brms (e.g., in 'stan/...' files) can serve as templates. No linked PRs or recent comments indicate progress, so this is a clean slate for a contributor.